stanza
stanza copied to clipboard
stanfordnlp
NER model training for Armenian
Is your feature request related to a problem? Please describe. I'm testing a trained NER model for Armenian for my project. After obtaining tangible results of its performance, this might be a valuable addition to the library.
It follows the dataset format and model characteristics defined by you.
Please, let me know if you have further testing guidelines and performance measures to validate the model's compatibility.
Which NER dataset?
If you build a charlm (which helps quite a bit on accuracy), please let us know what data you use as input text.
On Sun, Dec 5, 2021 at 8:16 AM Hovhannisian @.***> wrote:
Is your feature request related to a problem? Please describe. I'm testing a trained NER model for Armenian for my project. After obtaining tangible results of its performance, this might be a valuable addition to the library.
It follows the dataset format and model characteristics defined by you.
Please, let me know if you have further testing guidelines and performance measures to validate the model's compatibility.
— You are receiving this because you are subscribed to this thread. Reply to this email directly, view it on GitHub https://github.com/stanfordnlp/stanza/issues/889, or unsubscribe https://github.com/notifications/unsubscribe-auth/AA2AYWORAVTG5F5K6M7VVOTUPOF7LANCNFSM5JM6CUVQ . Triage notifications on the go with GitHub Mobile for iOS https://apps.apple.com/app/apple-store/id1477376905?ct=notification-email&mt=8&pt=524675 or Android https://play.google.com/store/apps/details?id=com.github.android&referrer=utm_campaign%3Dnotification-email%26utm_medium%3Demail%26utm_source%3Dgithub.
If you ever found a useful NER dataset, we'd be happy to include it in stanza.
A user sent us a pull request using an NER annotation of armtdp, which is now included in 1.5.0
https://github.com/stanfordnlp/stanza/pull/1212/commits/bb17958d09456fbb684efe8f1f9dd683f190cf2c